Skip to content

CMU/ARPAbet Pronouncing Dictionary stress/prosody now work correctly #170

@Skino1337

Description

@Skino1337

Checks

  • This template is only for bug reports, usage problems go with 'Help Wanted'.
  • I have thoroughly reviewed the project documentation but couldn't find information to solve my problem.
  • I have searched for existing issues, including closed ones, and couldn't find a solution.
  • I am using English to submit this issue to facilitate community communication.

Environment Details

Win 11, python 3.12, torch==2.11.0+cu126 torchaudio==2.11.0+cu126

Steps to Reproduce

Это [Z AA1 M AO0 K], а это [Z AA0 M AO1 K], и это [Z AA M AO K].

In this text, word ZAMOK sounds same, but does not!
In first variant stress must be on A char, is second on Ochar.

code & data to reproduce:

cwd = Path.cwd()
ref_audio_path = cwd / 'SKLAVENWACHE.wav'
ref_text = 'Старые дома примкнут к тому, кто победит, как и всегда.  Многие шепчутся, что он бастард, не имеющий на него прав.  Ты был во многих борделях разных городов.  Вестерос уязвим, как никогда.'
ttext = 'Это [Z AA1 M AO0 K], а это [Z AA0 M AO1 K], и это [Z AA M AO K].'
output_file_path = cwd / 'result.wav'
output_file_path.unlink(missing_ok=True)

gothic_voice_omni.zip

✔️ Expected Behavior

No response

❌ Actual Behavior

No response

Metadata

Metadata

Assignees

No one assigned

    Labels

    bugSomething isn't working

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions